Choosing between man- and zone coverage is one of the most important strategic decisions of a defensive coordinator prior to each play in American football. While experienced coaches and quarterbacks can often identify these defensive strategies visually, the growing availability of tracking data presents another opportunity to infer the underlying tactic. This project aims to leverage hidden Markov models (HMMs) to detect defensive strategies — man or zone coverage — based on pre-snap player movement data. By modeling hidden states that represent the offensive player to be guarded, this approach provides a data-driven framework for unraveling the complexity of defensive patterns and enables real-time tactical insights for coaching and analysis.
This video displays a touchdown from the Kansas City Chiefs against the Arizona Cardinals in Week 1 of the 2022 NFL season. We can see that, pre-snap, Mecole Hardman (KC #17) travels from the left side to the right side, followed by the defender Marco Wilson (AZ #20), i.e. a clear indication for man-coverage.